English
Related papers

Related papers: Improved Bounds for Private and Robust Alignment

200 papers

Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities. This emerging compatibility between independently trained models introduces new…

Artificial Intelligence · Computer Science 2026-05-26 Matt Gorbett , Suman Jana

Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples. Our work draws the connection between optimal robust learning and the privacy-utility tradeoff…

Machine Learning · Computer Science 2021-05-20 Ye Wang , Shuchin Aeron , Adnan Siraj Rakin , Toshiaki Koike-Akino , Pierre Moulin

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Computation and Language · Computer Science 2026-04-21 Anmol Goel , Cornelius Emde , Sangdoo Yun , Seong Joon Oh , Martin Gubri

It is of soaring demand to develop statistical analysis tools that are robust against contamination as well as preserving individual data owners' privacy. In spite of the fact that both topics host a rich body of literature, to the best of…

Statistics Theory · Mathematics 2022-09-01 Mengchu Li , Thomas B. Berrett , Yi Yu

Personalization in language models aims to tailor model behavior to individual users or user groups. Prompt-based methods incorporate user preferences into queries, while training-based methods encode them into model parameters. Model…

Computation and Language · Computer Science 2025-09-22 Kyuyoung Kim , Jinwoo Shin , Jaehyung Kim

A Private Repetition algorithm takes as input a differentially private algorithm with constant success probability and boosts it to one that succeeds with high probability. These algorithms are closely related to private metaselection…

Cryptography and Security · Computer Science 2024-10-28 Kunal Talwar

We study online alignment of large language models under misspecified preference feedback, where the observed preference oracle deviates from an ideal but unknown ground-truth oracle. The online LLM alignment problem is a bi-level…

Machine Learning · Computer Science 2026-02-25 Zimeng Li , Mudit Gaur , Vaneet Aggarwal

Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in…

Cryptography and Security · Computer Science 2025-09-03 Honghui Xu , Kaiyang Li , Wei Chen , Danyang Zheng , Zhiyuan Li , Zhipeng Cai

Nowadays, large language models (LLMs) have been integrated with conventional recommendation models to improve recommendation performance. However, while most of the existing works have focused on improving the model performance, the…

Computation and Language · Computer Science 2024-06-04 Sichun Luo , Wei Shao , Yuxuan Yao , Jian Xu , Mingyang Liu , Qintong Li , Bowei He , Maolin Wang , Guanzhi Deng , Hanxu Hou , Xinyi Zhang , Linqi Song

Machine learning systems can produce personalized outputs that allow an adversary to infer sensitive input attributes at inference time. We introduce Robust Privacy (RP), an inference-time privacy notion inspired by certified robustness: if…

Machine Learning · Computer Science 2026-01-27 Jiankai Jin , Xiangzheng Zhang , Zhao Liu , Deyue Zhang , Quanchen Zou

Algorithmic robust statistics has traditionally focused on the contamination model where a small fraction of the samples are arbitrarily corrupted. We consider a recent contamination model that combines two kinds of corruptions: (i) small…

Data Structures and Algorithms · Computer Science 2024-10-23 Thanasis Pittas , Ankit Pensia

We study linear contextual bandits under adversarial corruption and heavy-tailed noise with finite $(1+\epsilon)$-th moments for some $\epsilon \in (0,1]$. Existing work that addresses both adversarial corruption and heavy-tailed noise…

Machine Learning · Computer Science 2026-03-17 Naoto Tani , Futoshi Futami

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Machine Learning · Computer Science 2025-10-17 Fatmazohra Rezkellah , Ramzi Dakhmouche

We study differentially private distributed optimization under communication constraints. A server using SGD for optimization aggregates the client-side local gradients for model updates using distributed mean estimation (DME). We develop a…

Machine Learning · Computer Science 2023-02-23 Antonious M. Girgis , Suhas Diggavi

Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward…

Machine Learning · Computer Science 2026-05-11 Lucas Monteiro Paes , Natalie Mackraz , Barry-John Theobald , Federico Danieli

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Artificial Intelligence · Computer Science 2025-04-08 Hao Du , Shang Liu , Lele Zheng , Yang Cao , Atsuyoshi Nakamura , Lei Chen

We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs). A number of recent works in privacy research have attempted…

Artificial Intelligence · Computer Science 2026-02-10 Soumi Das , Camila Kolling , Mohammad Aflah Khan , Mahsa Amani , Bishwamittra Ghosh , Qinyuan Wu , Till Speicher , Krishna P. Gummadi

Offline reinforcement learning (RL) is vulnerable to real-world data corruption, with even robust algorithms failing under challenging observation and mixture corruptions. We posit this failure stems from data corruption creating sharp…

Machine Learning · Computer Science 2026-04-08 Le Xu , Jiayu Chen

Distributed online learning is gaining increased traction due to its unique ability to process large-scale datasets and streaming data. To address the growing public awareness and concern on privacy protection, plenty of algorithms have…

Machine Learning · Computer Science 2024-08-27 Ziqin Chen , Yongqiang Wang

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

Machine Learning · Statistics 2022-10-18 Jiayuan Ye , Reza Shokri